© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20736
    Prev
    Next
    INDEX
    Explanations

    delegated reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Со
    0.56
    тыми
    0.55
     завода
    0.55
    \}\
    0.52
    но
    0.50
    со
    0.50
    짭
    0.49
    ро
    0.49
     شراب
    0.48
     фабри
    0.47
    POSITIVE LOGITS
     privilege
    0.48
     refer
    0.46
     delegated
    0.46
     reference
    0.45
     anteced
    0.45
     espes
    0.45
     delegate
    0.44
    जिब
    0.43
     momentous
    0.43
     referendum
    0.42
    Activations Density 0.006%

    No Known Activations